<no title> — Group 14 Final Project Analysis of Tobacco Sales

# import cleaned-up tobacco average sales data
states_sales = tobacco_data_import()

# change format of data
sub = states_sales.groupby(['LocationDesc', 'LocationAbbr', 'DataValueUnit']).apply(lambda row: pd.Series({"2013": row.DataValue[row.YearStart == 2013].values[0],
                                                                   "2014": row.DataValue[row.YearStart == 2014].values[0],
                                                                   # ignoring 2015 because missing data in the original source
                                                                   "2016": row.DataValue[row.YearStart == 2016].values[0],
                                                                   "2017": row.DataValue[row.YearStart == 2017].values[0],
                                                                   "2018": row.DataValue[row.YearStart == 2018].values[0],
                                                                    "2019": row.DataValue[row.YearStart == 2019].values[0]}))

sub =sub.reset_index(['LocationDesc', 'LocationAbbr', 'DataValueUnit'], drop=False)
sub.head()

	LocationDesc	LocationAbbr	DataValueUnit	2013	2014	2016	2017	2018	2019
0	Alabama	AL	pack sales per capita	64.6	61.7	60.1	58.1	54.7	53.1
1	Alaska	AK	pack sales per capita	39	37.2	35.6	32.9	31.1	30.4
2	Arizona	AZ	pack sales per capita	24.4	23	23.1	22.5	21.8	20.7
3	Arkansas	AR	pack sales per capita	57.5	54.4	54.2	52.4	50.2	47.6
4	California	CA	pack sales per capita	23.9	22.7	22	20.5	16.6	15.8

median_income = income_data_import()

# avg sales (sales per capita) for each year (6 in total)

# Year 2015 omitted
Years = [2013, 2014, 2016, 2017, 2018, 2019]
year = 0

# plotting 6 graphs in 2013, 2014, 2016, 2017, 2018, and 2019
for index in range(3, 9):
    
    ddf = sub.iloc[:, index].astype(float)
    
    fig =  px.choropleth(sub,
                         locations="LocationAbbr",
                         hover_name="LocationDesc",
                         color= ddf.values,
                         locationmode='USA-states',
                         color_continuous_scale='greens',
                         range_color = (80000, 40000))

    fig.update_layout(title_text = f"Sales per capita in {Years[year]}", geo_scope='usa')

    fig.write_html(f"output/avgSales{Years[year]}.html")
    year += 1
    #fig.show()

# show output plot for 2013
putHTML(year = 2013, avg_sales = True)

# median income graph for each year (6 in total)
Years1 = [2013, 2014, 2015, 2016, 2017, 2018, 2019]
year = 0

# plotting 7 graphs in 2013 to 2019
for index in reversed(range(1, 8)):
    ddf = median_income.iloc[:, index].astype(float)

    fig = px.choropleth(median_income,
                         locations="state",
                         hover_name="Location",
                         color=ddf.values,
                         locationmode='USA-states',
                         color_continuous_scale='reds',
                         range_color = (80000, 40000))

    fig.update_layout(title_text = f"Median Income in {Years1[year]}", geo_scope='usa')

    fig.write_html(f"output/medianIncome{Years1[year]}.html")
    year += 1
    #fig.show()

# show output plot for 2013
putHTML(year = 2013, avg_sales = False)

Contents